CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

semgrep

Run Semgrep static analysis on a codebase with capability-checked workers. Supports two scan modes — "run all" (full ruleset coverage) and "important only" (high-confidence security vulnerabilities). Records local Semgrep Pro evidence and uses the approved engine. Use when asked to scan code for vulnerabilities, run a security audit with Semgrep, find bugs, or perform static analysis. Uses parallel workers when authorized and supported, with bounded direct execution as a fallback.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/cloud-profile/skills/semgrep/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-organized and highly actionable for a complex orchestration skill, with a clear gated 5-step workflow and a thorough success checklist. Its main problems are redundancy (diagram vs. workflow table, hard-gate restated five times) and a broken bundle reference: the detailed workflow file `workflows/scan-workflow.md` is cited as the primary instruction source but is missing from the bundle, and the helper scripts are not indexed.

Suggestions

Fix or remove the dangling `workflows/scan-workflow.md` reference — the file does not exist in the bundle; either add the detailed 5-step workflow file or inline the detailed steps into SKILL.md.

Deduplicate the Step 3 approval-gate guidance (currently restated in Essential Principles, Workflow, Task tracking, Rationalizations to Reject, and Success Criteria) and drop the ASCII orchestration diagram, which repeats the Workflow table's content.

Add `scripts/scan-status.sh` (the `wait_semgrep_scans` source) and `scripts/merge_sarif.py` to the Reference Index so every bundle file is discoverable from SKILL.md.

DimensionReasoningScore

Conciseness

The body is dense and almost entirely skill-specific policy (no generic concept explanations), but it could be tightened: the ASCII orchestration diagram duplicates the Workflow table's five steps, the Step-3 hard gate is restated in at least five places (Essential Principles, Workflow, Task tracking, Rationalizations, Success Criteria), and the 13-row "Rationalizations to Reject" table repeats Principles 2–4. This fits "mostly efficient but includes some unnecessary explanation or could be tightened"; a 4 would require only minor trimmable instances.

3 / 5

Actionability

Mostly executable guidance: `command -v semgrep`, `SEMGREP_ENABLE_VERSION_CHECK=0 semgrep --metrics=off --version`, a copy-paste output-directory resolution block, `--severity MEDIUM --severity HIGH --severity CRITICAL` flags, and `uv run {baseDir}/scripts/merge_sarif.py $OUTPUT_DIR/raw $OUTPUT_DIR/results/results.sarif`. Minor gaps remain — Step 1 language detection is described only as "Supported file search" with no command, and the detailed execution process is delegated to a workflow file that is not in the bundle.

4 / 5

Workflow Clarity

The five steps are clearly sequenced with an explicit hard gate at Step 3, per-step references, task-tracking guidance, and a 15-item Success Criteria checklist including validation (fresh JSON/SARIF pairs passed `wait_semgrep_scans`, `results.sarif` valid JSON). However, the body states "Follow the detailed workflow in [scan-workflow.md]" and that file does not exist, so the summary table carries the sequence alone and checkpoint detail (error-recovery loops) is only implicit in the checklist — clear sequence with minor validation gaps rather than a full 5.

4 / 5

Progressive Disclosure

Section structure is good and the three references/ files are real, clearly signaled, and indexed, but the bundle structure has real defects: `workflows/scan-workflow.md` is referenced twice (Workflow section and Reference Index) yet does not exist — a dangling pointer to the skill's core detailed process — and `scripts/scan-status.sh` plus `scripts/merge_sarif.py` are absent from the Reference Index (scan-status is only alluded to as "the bundled scan-status helper"). Structure is present but navigation fails at the most important reference point.

3 / 5

Total

14

/

20

Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person voice, concrete capabilities, and an explicit "Use when" clause with natural trigger phrases anchored to the Semgrep tool name. The only weaknesses are a few missing trigger synonyms ("security scan", "SAST") and unqualified generic triggers ("find bugs") that create slight overlap risk with other static-analysis skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "Run Semgrep static analysis", two named scan modes with coverage semantics ("run all" / "important only"), "Records local Semgrep Pro evidence", and "Uses parallel workers... with bounded direct execution as a fallback" — comprehensively covering the skill's capability space. It matches the anchor for multiple specific concrete actions with comprehensive coverage; a 4 would require noticeable coverage gaps, which are absent.

5 / 5

Completeness

Both questions are answered explicitly: the "what" ("Run Semgrep static analysis... Supports two scan modes... Records local Semgrep Pro evidence") and the "when" via a concrete "Use when asked to scan code for vulnerabilities, run a security audit with Semgrep, find bugs, or perform static analysis" clause. This clearly matches the top anchor for explicit what AND when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural trigger phrases are present: "scan code for vulnerabilities", "run a security audit with Semgrep", "find bugs", "perform static analysis" — phrasing users would actually say. A few natural variants are missing (e.g., "security scan", "SAST", "code audit"), which fits the anchor for good keyword coverage with a few natural terms missing rather than comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The tool is named explicitly in both the capability statement and the trigger ("security audit with Semgrep"), giving it a clear niche. However, the unqualified triggers "find bugs" and "perform static analysis" could also match other security-analysis or linting skills, so it is mostly distinct with minor overlap risk rather than minimal conflict risk.

4 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 possibly missing (workflows/scan-workflow.md)

Warning

Total

15

/

16

Passed

Repository

BigSimmo/PsychSift

Path

.claude/cloud-profile/skills/semgrep/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.